VIETNAM NATIONAL UNIVERSITY HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY FACULTY OF COMPUTER SCIENCE AND ENGINEERING CAPSTONE PROJECT A MOBILE APP FOR CITY SMART PARKING SYSTEM Major: Computer Science Committee: Computer Science 4 Supervisor: Assoc. Tran Minh Quang Reviewer: M. Truong Quynh Chi —o0o— Student 1: Le Hoang Thuy - 1952130 Student 2: Doan Hoang Thien - 2053450 Ho Chi Minh City, Dec 2024 TRƯỜNG ĐẠI HỌC BÁCH KHOA CỘNG HÒA XÃ HỘI CHỦ NGHĨA VIỆT NAM KHOA KH & KT MÁY TÍNH Độc lập - Tự do - Hạnh phúc ---------------------------- Ngày 18 tháng 12 năm 2024 PHIẾU CHẤM BẢO VỆ LVTN (Dành cho người hướng dẫn/phản biện) 1. Họ và tên SV: Lê Hoàng Thụy MSSV: 1952130 Doãn Hoàng Thiên MSSV: 2053450 Ngành (chuyên ngành): Khoa học Máy tính 2.
Đề tài: A mobile app for city smart parking system 3. Họ tên người hướng dẫn: Assoc. Trần Minh Quang 4. Tổng quát về bản thuyết minh: Số trang: Số chương: Số bảng số liệu: Số hình vẽ: Số tài liệu tham khảo: Phần mềm tính toán: Hiện vật (sản phẩm): 5.
Tổng quát về các bản vẽ: - Số bản vẽ: Bản A1: Bản A2: Khổ khác: - Số bản vẽ vẽ tay Số bản vẽ trên máy tính: 6. Những ưu điểm chính của LVTN (Advantages): - Analyze, design and implement a smart parking system as a mobile app - Propose methods for parking lot availability prediction - Investigate and propose a routing mechanism which helps user to find parking lot conveniently - Evaluate the proposed solutions. Những thiếu sót chính của LVTN (Weakness): - The routing method is still simple as real-time traffic information has not been taken into account - Lack of evaluation data. The proposed approaches should be evaluated more thoroughly in different scenarios and data - The proposed approaches have not been integrated into Utraffic.
Đề nghị: Được bảo vệ Bổ sung thêm để bảo vệ Không được bảo vệ 9. 3 câu hỏi SV phải trả lời trước Hội đồng: 10. Đánh giá chung (bằng chữ: giỏi, khá, TB): Good (Giỏi); Điểm: 8. Trần Minh Quang Acknowledgement We extend our deepest appreciation to Assoc.
Tran Minh Quang for his invaluable support throughout our smart parking system. Minh Quang’s thoughtful and dedicated guidance has been instrumental to our project’s success. His expertise in the field of smart parking systems has provided us with in- valuable insights and a deeper understanding of our project’s intricacies. He has been proactive in addressing our queries and has offered invaluable assistance in overcoming challenges en- countered during our research journey.
Minh Quang has facilitated opportunities for collaboration with specialized groups and fellow graduate students, granting us access to significant scientific resources and enriching research materials. The knowledge and experience imparted by Assoc. Minh Quang will undoubtedly serve as invaluable assets for our future endeavors. We also extend our heartfelt gratitude to Ho Chi Minh City University of Technology - Vietnam National University for providing us with a conducive environment for studying and conducting research.
The knowledge and skills acquired during our time at the university have been invaluable in shaping our academic and professional growth. We are deeply appreciative of the opportunities afforded to us, which have contributed significantly to our development. Supervisor’s signature Associate Professor, Tran Minh Quang 1 Declaration of Authenticity This capstone project is the culmination of our independent research and efforts, with due attribution given to materials sourced from external references in accordance with Vietnam National University - Ho Chi Minh City University of Technology. The project, unless stated otherwise, is an original creation and has not been submitted for any academic or professional credentials.
The opinions expressed in this project solely belong to the author and do not necessarily reflect the views of Vietnam National University - Ho Chi Minh City University of Technology. The author takes full responsibility for any potential errors or oversights in this work. Ho Chi Minh City, May 2024 Lê Hoàng Thụy Doãn Hoàng Thiên Abstract With the rapid urbanization and the increasing number of vehicles on the roads, efficient management of parking spaces has become a critical aspect of urban mobility. This project presents a Smart Parking System (SPS) designed to address the challenges associated with tra- ditional parking methods and enhance the overall parking experience for both drivers and city planners.
The proposed Smart Parking System leverages advanced technologies such as Internet of Things (IoT), sensors, and real-time data processing to optimize parking space utilization. A network of sensors is deployed in parking lots to monitor the availability of individual park- ing spaces. The collected data is transmitted to a centralized cloud-based platform, where it is processed in real-time to provide accurate and up-to-date information about parking space occupancy. Drivers can access the parking availability information through a user-friendly mobile ap- plication or electronic displays strategically placed throughout the city.
This allows them to make informed decisions about where to find parking, reducing the time spent searching for a suitable spot and minimizing traffic congestion. City planners benefit from the system’s analytics capabilities, which provide insights into parking patterns, peak usage times, and overall parking space utilization. This data can be used to optimize urban planning strategies, allocate resources efficiently, and implement policies that address the specific parking needs of different areas within the city. Furthermore, the Smart Parking System promotes sustainability by minimizing unnecessary vehicle emissions and fuel consumption associated with circling for parking.
The system also supports payment integration, enabling cashless transactions and enhancing the overall conve- nience of the parking process. In conclusion, the Smart Parking System presented in this project offers a comprehensive solution to the challenges of urban parking management. By harnessing the power of IoT and real-time data processing, it not only improves the efficiency of parking space utilization but also contributes to a more sustainable and seamless urban mobility experience. Contents Acknowledgement 1 Supervisor’s signature 1 Declaration of Authenticity 1 Abstract 1 1 Introduction 1 1.1 Background and context .1 Aims and objectives .3 Description of the Remaining Chapters .1 Smart parking sensors and tools .3 Inductive loop detectors .4 Parking guidance systems .5 Radio frequency tags .2 Smart parking technology .1 Global positioning system (GPS) .3 Vehicular ad hoc networks (VANET) .4 Multi-agent systems .3 Smart parking applications .3 DFPS - A Distributed Mobile System For Free Parking Assignment [31] 16 2.4 Research gap discussion.
20 3 Requirement analysis and detailed specification of use cases 22 3.3 Non-Functional Requirement .4 Use case diagram. 41 4 System analysis and design 44 4.2 Smart parking system workflow .1 Open parking space .2 Closed parking space .3 Smart parking system design .2 Predictive Analytics Modules .1 Mobile app design .3 Parking spaces management. 59 5 Predictive Analysis of Parking Lot Occupancy 60 5.1 Data Source and Collection .3 Exploratory Data Analysis .5 Preprocessing and Enhancements .3 Occupancy Prediction Implementation .2 Gradient Boosting Model .1 Introducing to Routing .1 Classical Routing Algorithms .2 Approaches gap disscussion .3 MCDM-Based Routing System for Smart Parking .1 Principles of Multi-Criteria Decision Making (MCDM) .2 Design of the MCDM-Based Routing System. 86 CAPSTONE PROJECT - ACADEMIC YEAR 2024 Page 2/135 Contents 6.2 Decision model formulation .3 Route calculation and Decision making .3 Implementation of MCDM-Based Routing System .1 Overview of the system flow .2 User location and destination Search .3 Searching for Nearby parking spots with OpenRouteService API .4 Route calculation to the selected parking spot .5 Multi-Criteria Decision-Making (MCDM) approach .6 OpenRouteService API mechanism .1 Criteria for evaluation .2 Accuracy in parking spot selection .5 Scalability and Adaptability .6 Real-time decision Mmking .5 Limitations and future improvements .1 Absence of Time Factor (Ti ) .2 Absence of cost factor (Ci ) .3 Lack of full customization .4 Potential future improvements.
93 7 Mobile Application Implementation 94 7.5 Flutter and Dart .6 OpenStreetMap API and OpenRouteService .3 Predictive Analysis Module .1 Training the Predictive Model .2 Creating an API for the Predictive Module .1 Destination Searching: Nominatim API Integration .2 Parking Spots Searching: Point of Interest (POI) API .3 Optimal parking spot selection: Direction API and Parking availability API. 110 CAPSTONE PROJECT - ACADEMIC YEAR 2024 Page 3/135 Contents 7.2 Pseudo-Code for distance calculation: .3 Parking availability prediction API .4 Pseudo-Code for parking availability: .5 Optimal parking spot scoring .6 Pseudo-Code for Route Scoring: .4 Routing to Parking Spot .2 Pseudo-Code for Routing: .3 Fetching the route: .4 Pseudo-Code for route fetching: .3 Finding parking spots .4 Calculating the score .5 Routing to the parking spot .6 Real-Time parking availability simulation .7 Integration of routing and parking availability models .9 Summary of features and advantages .1 iOS Application Evaluation .2 Execution time measurements .4 Network data usage .1 Strengths and innovations .2 Limitations and challenges. 130 Bibliography 131 CAPSTONE PROJECT - ACADEMIC YEAR 2024 Page 4/135 List of Figures 3.1 Driver use case diagram for the smart parking system .2 Parking owner use case diagram for the smart parking system .3 Activity Diagram: Check in Process .4 Activity Diagram: Check out Process .5 Activity Diagram: Book a parking space .6 Activity Diagram: Casual Payment Gateway .7 Activity Diagram: ETC Payment Gateway .2 Open parking space system overview .3 Closed parking space system overview .1 Line Plot: Displays occupancy levels over time, emphasizing daily and weekly pattern .2 Bar Chart: Illustrates average occupancy by day of the week.3 Heatmap: Shows hourly occupancy trends across facilities, highlighting peak and off-peak times.4 Line Plot: Displays occupancy trends for each facility type across the 24-hour cycle.5 Stacked Bar Chart: Highlights differences in occupancy rates by facility type.6 Heatmap: Visualizes hourly occupancy variations, distinguishing patterns for weekdays and weekends.7 Architecture of gradient boosting.8 Architecture of LSTM (Long Short-Term Memory).15 Visualization of the user’s location on the map.16 Visualization of destination input. 118 List of Figures 7.17 Visualization of parking spots around the destination.18 Visualization of parking spots with details: name, distance, and availability score.19 Visualization of the optimal route from the user’s location to the parking spot.20 Visualization of priority adjustment.21 Visualization of future User login UI.22 Instruments: Performance analysis tool for IOS App .23 The aLot application on iOS takes 107.8 MB of storage.24 Cellular on Iphone.25 Reset the statistics to zero.
126 CAPSTONE PROJECT - ACADEMIC YEAR 2024 Page 6/135 List of Tables 2.1 Literature reviews on smart parking sensors and technologies .2 Strengths and Weakness of smart parking tools and technologies summary.3 Smart parking applications and their use of technologies and sensors.1 General use cases description for the whole system .2 Use case scenario for "Login" .3 Use case scenario for "Map" .4 Use case scenario for "Account management" .5 Use case scenario for "Customer support" .6 Use case scenario for "Register" .7 Use case scenario for "Live communication" .8 Use case scenario for "Parking space reservation" .9 Use case scenario for "Searching vehicle location" .10 Use case scenario for "Checkin/ Check out" .11 Use case scenario for "Parking space management" .12 Use case scenario for "Parking space reservation management" .13 Use case scenario for "View report" .1 Execution time measurements for aLot iOS.2 Data usage measurements for aLot iOS.1 Background and context The rapid pace of urbanization worldwide has significantly increased the number of vehicles on city roads, intensifying issues such as traffic congestion and parking shortages. Studies reveal that drivers spend substantial amounts of time searching for available parking spaces, which contributes to worsening traffic conditions, elevated air pollution levels, and diminished urban efficiency. Traditional parking management systems have proven inadequate in addressing the dynamic needs of urban environments. These systems often rely on manual processes, which result in in- accurate information about parking availability and inefficient allocation of resources.
The lack of real-time data integration and proactive management strategies exacerbates the difficulties faced by both drivers and parking operators, leading to further inefficiencies. To tackle these challenges, the concept of Smart Parking Systems (SPS) has gained signif- icant traction.
